brainpy.math.segment_sum
brainpy.math.segment_sum#
- brainpy.math.segment_sum(data, segment_ids, num_segments=None, indices_are_sorted=False, unique_indices=False, bucket_size=None, mode=None)[source]#
segment_sum
operator for brainpy Array and Variable.- Parameters
data (Array) – An array with the values to be reduced.
segment_ids (Array) – An array with integer dtype that indicates the segments of data (along its leading axis) to be summed. Values can be repeated and need not be sorted.
num_segments (Optional, int) – An int with nonnegative value indicating the number of segments. The default is set to be the minimum number of segments that would support all indices in
segment_ids
, calculated asmax(segment_ids) + 1
. Since num_segments determines the size of the output, a static value must be provided to usesegment_sum
in ajit
-compiled function.indices_are_sorted (bool) – whether
segment_ids
is known to be sorted.unique_indices (bool) – whether segment_ids is known to be free of duplicates.
bucket_size (int) – Size of bucket to group indices into.
segment_sum
is performed on each bucket separately to improve numerical stability of addition. DefaultNone
means no bucketing.mode (lax.GatherScatterMode) – A
jax.lax.GatherScatterMode
value describing how out-of-bounds indices should be handled. By default, values outside of the range [0, num_segments) are dropped and do not contribute to the sum.
- Returns
output – An array with shape
(num_segments,) + data.shape[1:]
representing the segment sums.- Return type
Array